Locality-constrained Linear Coding for image classification
Jinjun Wang, Jianchao Yang, Kai Yu et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2010
The traditional SPM approach based on bag-of-features (BoF) requires nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM. LLC utilizes the locality constraints to project each descriptor into its local-coordinate system, and the projected coordinates are integrated by max pooling to generate the final representation. With linear classifier, the proposed approach performs remarkably better than the traditional nonlinear SPM, achieving state-of-the-art performance on several benchmarks. Compared with the sparse coding strategy [22], the objective function used by LLC has an analytical solution. In addition, the paper proposes a fast approximated LLC method by first performing a K-nearest-neighbor search and then solving a constrained least square fitting problem, bearing computational complexity of O(M + K2). Hence even with very large codebooks, our system can still process multiple frames per second. This efficiency significantly adds to the practical values of LLC for real applications.
Cited by 3,067 works. doi:10.1109/cvpr.2010.5540018
Authors
References
- Histograms of Oriented Gradients for Human Detection
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Nonlinear Dimensionality Reduction by Locally Linear Embedding
- Caltech-256 Object Category Dataset
- Video Google: a text retrieval approach to object matching in videos
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
- The PASCAL visual object classes challenge 2006 (VOC2006) results
- Visual categorization with bags of keypoints
- Linear spatial pyramid matching using sparse coding for image classification
- The pyramid match kernel: discriminative classification with sets of image features